Length of Trend - Panel Data

Question

I have a well balanced panel data set which contains NA observations. I will be using LOCF, and would like to know how many consecutive NA\'s are in each panel, before carry

Answer 1

This will do it:

data[, max(with(rle(is.na(x)), lengths[values])), by = id]

I just ran rle to find all consecutive NA's and picked the max length.

---

Here's a rather convoluted answer to the comment question of recovering the date ranges for the above max:

data[, {
         tmp = rle(is.na(x));
         tmp$lengths[!tmp$values] = 0;  # modify rle result to ignore non-NA's
         n = which.max(tmp$lengths);    # find the index in rle of longest NA sequence

         tmp = rle(is.na(x));                   # let's get back to the unmodified rle
         start = sum(tmp$lengths[0:(n-1)]) + 1; # and find the start and end indices
         end   = sum(tmp$lengths[1:n]);

         list(date[start], date[end], max(tmp$lengths[tmp$values]))
       }, by = id]

Answer 2

You can use rle with the modification suggested here (and pasted below) to count NA values.

foo  <- data[, rle(x), by=id]
foo[is.na(values), max(lengths), by=id]

#     id V1
# 1:  1  1
# 2:  2  3
# 3:  3  3
# 4:  4  3
# 5:  5  4
# 6:  6  5
# 7:  7  3
# 8:  8  5
# 9:  9  2
# 10: 10  2

Amended rle function:

rle<-function (x)
{
     if (!is.vector(x)&&  !is.list(x))
         stop("'x' must be an atomic vector")
     n<- length(x)
     if (n == 0L)
         return(structure(list(lengths = integer(), values = x),
             class = "rle"))

     #### BEGIN NEW SECTION PART 1 ####
     naRepFlag<-F
     if(any(is.na(x))){
         naRepFlag<-T
         IS_LOGIC<-ifelse(typeof(x)=="logical",T,F)

         if(typeof(x)=="logical"){
             x<-as.integer(x)
             naMaskVal<-2
         }else if(typeof(x)=="character"){
             naMaskVal<-paste(sample(c(letters,LETTERS,0:9),32,replace=T),collapse="")
         }else{
             naMaskVal<-max(0,abs(x[!is.infinite(x)]),na.rm=T)+1
         }

         x[which(is.na(x))]<-naMaskVal
     }
     #### END NEW SECTION PART 1 ####

     y<- x[-1L] != x[-n]
     i<- c(which(y), n)

     #### BEGIN NEW SECTION PART 2 ####
     if(naRepFlag)
         x[which(x==naMaskVal)]<-NA

     if(IS_LOGIC)
         x<-as.logical(x)
     #### END NEW SECTION PART 2 ####

     structure(list(lengths = diff(c(0L, i)), values = x[i]),
         class = "rle")
}